[R-package] skip integer categorical feature check when building dataset subset (fixes #6412)

R-package/R/lgb.Dataset.R

@@ -170,7 +170,8 @@ Dataset <- R6::R6Class(
 
  # Check if more categorical features were output over the feature space
  data_is_not_filename <- !is.character(private$raw_data)
- if (data_is_not_filename && max(private$categorical_feature) > ncol(private$raw_data)) {
+ from_raw_data <- !is.null(private$raw_data) && is.null(private$used_indices)
+ if (data_is_not_filename && from_raw_data && max(private$categorical_feature) > ncol(private$raw_data)) {
  stop(
  "lgb.Dataset.construct: supplied a too large value in categorical_feature: "
  , max(private$categorical_feature)

R-package/tests/testthat/test_basic.R

@@ -3652,6 +3652,28 @@ test_that("lgb.cv() only prints eval metrics when expected to", {
  )
 })
 
+test_that("lgb.cv() works with an already constructed dataset with integer categoricals", {
+ data("mtcars")
+ y <- mtcars$mpg
+ x <- as.matrix(mtcars[, -1L])
+ categorical_feature <- which(names(mtcars) %in% c("cyl", "vs", "am", "gear", "carb")) - 1L
+ dtrain <- lgb.Dataset(
+ data = x
+ , label = y
+ , categorical_feature = categorical_feature
+ , free_raw_data = TRUE
+ , params = list(num_threads = .LGB_MAX_THREADS)
+ )
+ dtrain$construct()
+ params <- list(
+ objective = "regression"
+ , num_leaves = 2L
+ , verbose = .LGB_VERBOSITY
+ , num_threads = .LGB_MAX_THREADS
+ )
+ lgb.cv(params = params, data = dtrain, nrounds = 1L)
+})
+
 test_that("lightgbm() changes objective='auto' appropriately", {
  # Regression
  data("mtcars")